Recurrent Neural Networks (RNNs) — particularly Long Short Term Memory (LSTM) RNNs — are a popular and very successful model for generating sequences. However, most LSTM based sequence generation techniques are currently not interactive and do not allow continuous control of the sequence generation, let alone in a gestural or expressive manner. This research investigates methods of realtime con...

We present a series of deep learning models for predicting user engagement with twitter content, as measured by the number of retweets for a given tweet. We train models based on classic LSTM-RNN and CNN architectures, along with a more complex bi-directional LSTM-RNN with attention layer. We show that the attention RNN performs the best with 61% validation accuracy, but that all three deep lea...

Accurate rainfall forecasting is critical because it has a great impact on people’s social and economic activities. Recent trends on various literatures shows that Deep Learning (Neural Network) is a promising methodology to tackle many challenging tasks. In this study, we introduce a brand-new data-driven precipitation prediction model called DeepRain. This model predicts the amount of rainfal...

The change of emotions is a temporal dependent process. In this paper, a Bimodal-LSTM model is introduced to take temporal information into account for emotion recognition with multimodal signals. We extend the implementation of denoising autoencoders and adopt the Bimodal Deep Denoising AutoEncoder modal. Both models are evaluated on a public dataset, SEED, using EEG features and eye movement ...

We introduce a neural network that represents sentences by composing their words according to induced binary parse trees. We use Tree-LSTM as our composition function, applied along a tree structure found by a fully differentiable natural language chart parser. Our model simultaneously optimises both the composition function and the parser, thus eliminating the need for externally-provided pars...

This paper focuses on comparing between using Support Vector Machine based ranking (SVMRank) and Bidirectional LongShort-Term-Memory (bi-LSTM) neuralnetwork based sequence labeling in building a state-of-the-art Arabic part-ofspeech tagging system. Using SVMRank leads to state-of-the-art results, but with a fair amount of feature engineering. Using bi-LSTM, particularly when combined with word ...

Recurrent Neural Networks (RNNs) have long been recognized for their potential to model complex time series. However, it remains to be determined what optimization techniques and recurrent architectures can be used to best realize this potential. The experiments presented take a deep look into Hessian free optimization, a powerful second order optimization method that has shown promising result...

The driving force behind the recent success of LSTMs has been their ability to learn complex and non-linear relationships. Consequently, our inability to describe these relationships has led to LSTMs being characterized as black boxes. To this end, we introduce contextual decomposition (CD), an interpretation algorithm for analysing individual predictions made by standard LSTMs, without any cha...

Recent years have seen a growing interest in player modeling for digital games. Goal recognition, which aims to accurately recognize players’ goals from observations of low-level player actions, is a key problem in player modeling. However, player goal recognition poses significant challenges because of the inherent complexity and uncertainty pervading gameplay. In this paper, we formulate play...

Recent advances in AI and robotics have claimed many incredible results with deep learning, yet no work to date has applied deep learning to the problem of liquid perception and reasoning. In this paper, we apply fully-convolutional deep neural networks to the tasks of detecting and tracking liquids. We evaluate three models: a single-frame network, multi-frame network, and a LSTM recurrent net...